🪐 SmolLM Collection A series of smol LLMs: 135M, 360M and 1.7B. We release base and Instruct models as well as the training corpus and some WebGPU demos • 12 items • Updated Dec 22, 2024 • 213
'Textbook Qualitiy' Datasets Collection High quality, education focused data sets for replicating the training process used on Microsoft Phi. • 6 items • Updated Sep 14, 2023